© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48367
    Prev
    Next
    INDEX
    Explanations

    non-English characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aspectRatio
    -1.34
    恐れ
    -1.31
    筈
    -1.28
     trattano
    -1.26
    ものに
    -1.23
    ようだ
    -1.23
     abband
    -1.23
    纔
    -1.21
    OLOGÍA
    -1.21
     республики
    -1.20
    POSITIVE LOGITS
    子は
    1.95
    子が
    1.80
     täv
    1.45
    は約
    1.42
     såg
    1.41
    子さん
    1.37
     senaste
    1.32
     berätt
    1.30
     största
    1.30
     پنجم
    1.28
    Activations Density 0.000%

    No Known Activations